© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4539
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.53
     regards
    -0.52
    ();)
    -0.48
    |};
    -0.46
    ksesta
    -0.46
    regard
    -0.46
     entanto
    -0.45
     regard
    -0.45
    قایناق‌لار
    -0.45
    gemaakt
    -0.45
    POSITIVE LOGITS
    <bos>
    0.68
     становника
    0.63
    InitVars
    0.60
    +#+#
    0.59
     Himo
    0.55
    ibatis
    0.53
    发表于
    0.52
     raya
    0.50
     lindos
    0.50
     stand
    0.50
    Activations Density 0.004%

    No Known Activations